INDEX

Explanations

descriptions of environments and settings

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pras

-0.15

utex

-0.14

ditor

-0.14

uards

-0.14

dess

-0.14

fty

-0.14

QUIRES

-0.14

vard

-0.14

vey

-0.14

POSITIVE LOGITS

aska

0.16

ilig

0.15

ember

0.14

onso

0.14

ienen

0.14

Sez

0.14

gre

0.14

uze

0.14

eyed

0.14

INTERFACE

0.14

Activations Density 0.331%

descriptions of environments and settings

No Comments

No Known Activations